Name: Nianlong Gu
Type: User
Company: ETH Zurich
Bio: Machine learning scientist at Universität Zürich. Experienced in NLP, information retrieval, LLM, and AI-based research in bioacoustics.
Location: Zurich, Switzerland
Blog: https://nianlonggu.com
Nianlong Gu's Projects
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
Master thesis project. In this project, an autoencoder model is designed to achieve single image super resolution.
A LaTeX title page template for a Ph.D. thesis at ETH Zurich.
Using the floating random walk method to extract the inter-connect capacitance in the VLSI
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Code and data for the work Controllable Citation Sentence Generation with Language Models, at 4th Workshop on Scholarly Document Processing at ACL 2024
Code for ECIR 2022 paper Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-based Reranking
Master thesis project. In this project, an autoencoder model is designed to achieve single image super resolution.
Code for ACL 2022 paper on the topic of long document summarization: MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes
Adapting an Efficient Long Document Extractive Summarizer for Document Question Answering
A template for two-column scientific preprints
WACV 2020 paper: Reverse Variational Autoencoder for Visual Attribute Manipulation and Anomaly Detection Pytorch Implementation
A code snippet for using the rouge-score bootstrapping sampling method to compute the confidence level of rouge scores
Parsers for scientific papers (PDF2JSON, TEX2JSON, JATS2JSON)
ACL23 Demo SciLit: A Platform for Joint Scientific Literature Discovery, Summarization and Citation Generation
Create a draggable and resizable dashboard in Streamlit, featuring Material UI widgets, Monaco editor (Visual Studio Code), Nivo charts, and more!
Analyze the image quality in the frequency domain and compare the performance of different SISR models
simple implementation of the support vector machine algorithm, for detail see my blog https://nianlonggu.com
A python library for voice activity detection (VAD) for speech/non-speech segmentation.
Code for ICASSP 2024 paper WhisperSeg: Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection